{"id":"https://openalex.org/W4224933323","doi":"https://doi.org/10.1109/icassp43922.2022.9747797","title":"Mining Hard Samples Locally And Globally For Improved Speech Separation","display_name":"Mining Hard Samples Locally And Globally For Improved Speech Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224933323","doi":"https://doi.org/10.1109/icassp43922.2022.9747797"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747797","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100436995","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0002-1617-5804"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051467915","display_name":"Yizhou Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Peng","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","Xinjiang Provincial Key Laboratory of Multi-Lingual Information Technology, Urumqi, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Provincial Key Laboratory of Multi-Lingual Information Technology, Urumqi, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,Urumqi,China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan","National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100436995"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.6079,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63759446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6037","last_page":"6041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6625174283981323},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6453595757484436},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6011543869972229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5921823382377625},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5544494986534119},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.5056650638580322},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4331437051296234},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4270496964454651},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38524729013442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3493785858154297},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33057841658592224},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3248613476753235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3061464726924896},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23332983255386353},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21769431233406067},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09582832455635071}],"concepts":[{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6625174283981323},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6453595757484436},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6011543869972229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5921823382377625},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5544494986534119},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5056650638580322},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4331437051296234},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4270496964454651},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38524729013442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3493785858154297},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33057841658592224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3248613476753235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3061464726924896},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23332983255386353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21769431233406067},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09582832455635071},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747797","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747797","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729722","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931406","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1999318832","https://openalex.org/W2107742354","https://openalex.org/W2118978333","https://openalex.org/W2142261479","https://openalex.org/W2148143831","https://openalex.org/W2167464971","https://openalex.org/W2221409856","https://openalex.org/W2406222150","https://openalex.org/W2440599146","https://openalex.org/W2460742184","https://openalex.org/W2509065397","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2775447965","https://openalex.org/W2798869704","https://openalex.org/W2890964092","https://openalex.org/W2896271387","https://openalex.org/W2931364255","https://openalex.org/W2947380870","https://openalex.org/W2952218014","https://openalex.org/W2962895364","https://openalex.org/W2962935966","https://openalex.org/W2963108767","https://openalex.org/W2963212406","https://openalex.org/W2963691377","https://openalex.org/W2970941190","https://openalex.org/W2972640480","https://openalex.org/W2972947281","https://openalex.org/W3035724871","https://openalex.org/W3096893582","https://openalex.org/W3098357269","https://openalex.org/W3099330747","https://openalex.org/W3132250316","https://openalex.org/W3161766157","https://openalex.org/W3162437887","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W6631190155","https://openalex.org/W6676029316","https://openalex.org/W6763430915","https://openalex.org/W6764733053","https://openalex.org/W6774687970","https://openalex.org/W6779304510","https://openalex.org/W6790920653"],"related_works":["https://openalex.org/W8451425","https://openalex.org/W6091113","https://openalex.org/W12783365","https://openalex.org/W2804300","https://openalex.org/W14471487","https://openalex.org/W2455099","https://openalex.org/W6105805","https://openalex.org/W325970","https://openalex.org/W13929034","https://openalex.org/W10622786"],"abstract_inverted_index":{"Speech":[0],"separation":[1,37,64,159],"dataset":[2],"typically":[3],"consists":[4],"of":[5,108,149,170],"hard":[6,43,71,84,99,109,116,171],"and":[7,10,15,28,69,102,145,188],"non-hard":[8,26],"samples,":[9],"the":[11,23,30,35,75,94,106,112,139,168,174,184,189,197],"former":[12],"is":[13,39],"minority":[14],"latter":[16],"majority.":[17],"The":[18],"data":[19,60],"imbalance":[20,61],"problem":[21],"biases":[22],"model":[24],"towards":[25],"samples":[27,44,85,110,172],"weakens":[29],"generalization":[31],"capability.":[32],"Given":[33],"that":[34,141,164],"average":[36,185],"performance":[38],"sufficiently":[40],"good,":[41],"improving":[42],"may":[45],"contribute":[46],"more":[47,193],"to":[48,58,81,104,126],"back-end":[49],"tasks.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,77,96,129],"propose":[55,78,130],"two":[56,150],"methods":[57,166],"alleviate":[59],"in":[62,90,111,122,152,173],"speech":[63],"task,":[65],"based":[66,137],"on":[67,138],"local":[68,127,198],"global":[70,98,190],"sample":[72,100,117],"mining.":[73],"For":[74,93],"local,":[76],"weighted":[79],"loss":[80,121],"compensate":[82],"for":[83],"by":[86],"increasing":[87],"their":[88],"weights":[89],"each":[91],"batch.":[92],"global,":[95],"perform":[97],"mining":[101,118],"re-sample":[103],"increase":[105],"proportion":[107],"training":[113],"set.":[114],"Because":[115],"using":[119,134,178],"objective":[120],"dynamic":[123,179],"mixing":[124,180],"leads":[125],"results,":[128],"an":[131],"indirect":[132],"method":[133,191],"speaker-specific":[135],"parameters,":[136],"fact":[140],"pitch":[142],"median":[143],"difference":[144],"x-vector":[146],"cosine":[147],"distance":[148],"speakers":[151],"a":[153],"mixture":[154],"are":[155],"closely":[156],"correlated":[157],"with":[158],"SI-SNRi.":[160],"Experimental":[161],"results":[162,195],"show":[163],"both":[165],"decrease":[167],"percentage":[169],"test":[175],"set":[176],"than":[177,196],"only":[181],"while":[182],"keeping":[183],"SI-SNRi":[186],"comparable,":[187],"shows":[192],"promising":[194],"one.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}